{"id":"https://openalex.org/W7125374400","doi":"https://doi.org/10.1145/3784828.3786264","title":"Performance and Programmability of MPI+X Integration with CUDA, HIP, SYCL, OpenACC, and OpenMP Offloading for Supercomputing: A Case Study on Dense Matrix\u2013Vector Multiplication","display_name":"Performance and Programmability of MPI+X Integration with CUDA, HIP, SYCL, OpenACC, and OpenMP Offloading for Supercomputing: A Case Study on Dense Matrix\u2013Vector Multiplication","publication_year":2026,"publication_date":"2026-01-22","ids":{"openalex":"https://openalex.org/W7125374400","doi":"https://doi.org/10.1145/3784828.3786264"},"language":"en","primary_location":{"id":"doi:10.1145/3784828.3786264","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3786264","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3784828.3786264","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033657134","display_name":"Ezhilmathi Krishnasamy","orcid":"https://orcid.org/0000-0002-1971-4973"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Ezhilmathi Krishnasamy","raw_affiliation_strings":["University of Luxembourg, Esch-sur-Alzette, Luxembourg and University of Ljubljana, ljubljana, Slovenia"],"raw_orcid":"https://orcid.org/0000-0002-1971-4973","affiliations":[{"raw_affiliation_string":"University of Luxembourg, Esch-sur-Alzette, Luxembourg and University of Ljubljana, ljubljana, Slovenia","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123588418","display_name":"James Throtter","orcid":null},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"James Throtter","raw_affiliation_strings":["Simula Research Laboratory, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0003-4498-020X","affiliations":[{"raw_affiliation_string":"Simula Research Laboratory, Oslo, Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xing Cai","orcid":"https://orcid.org/0000-0003-3706-4414"},"institutions":[{"id":"https://openalex.org/I2799829267","display_name":"Simula Research Laboratory","ror":"https://ror.org/00vn06n10","country_code":"NO","type":"facility","lineage":["https://openalex.org/I2799829267"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Xing Cai","raw_affiliation_strings":["University of Oslo, Oslo, Norway and Simula Research Laboratory, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0003-3706-4414","affiliations":[{"raw_affiliation_string":"University of Oslo, Oslo, Norway and Simula Research Laboratory, Oslo, Norway","institution_ids":["https://openalex.org/I2799829267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123559743","display_name":"Dirk Pleiter","orcid":null},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dirk Pleiter","raw_affiliation_strings":["University of Groningen, Groningen, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-7296-7817","affiliations":[{"raw_affiliation_string":"University of Groningen, Groningen, Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034097340","display_name":"Leon Kos","orcid":null},"institutions":[{"id":"https://openalex.org/I153976015","display_name":"University of Ljubljana","ror":"https://ror.org/05njb9z20","country_code":"SI","type":"education","lineage":["https://openalex.org/I153976015"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Leon Kos","raw_affiliation_strings":["University of Ljubljana, Ljubljana, Slovenia"],"raw_orcid":"https://orcid.org/0000-0002-1790-7093","affiliations":[{"raw_affiliation_string":"University of Ljubljana, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I153976015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029089983","display_name":"Laura Saavedra","orcid":"https://orcid.org/0000-0001-7323-309X"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Laura Saavedra","raw_affiliation_strings":["University of Santiago de Compostela, Santiago de Compostela, Spain"],"raw_orcid":"https://orcid.org/0000-0001-7323-309X","affiliations":[{"raw_affiliation_string":"University of Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121773374","display_name":"Pascal Bouvry","orcid":null},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Pascal Bouvry","raw_affiliation_strings":["University of Luxembourg, Esch-sur-Alzette, Luxembourg"],"raw_orcid":"https://orcid.org/0000-0001-9338-2834","affiliations":[{"raw_affiliation_string":"University of Luxembourg, Esch-sur-Alzette, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9370999932289124,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9370999932289124,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.01730000041425228,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.00839999970048666,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6679999828338623},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.588100016117096},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5555999875068665},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.47269999980926514},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.43070000410079956},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.375},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3562000095844269},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.34850001335144043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8457000255584717},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6679999828338623},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6037999987602234},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.588100016117096},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5217999815940857},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.43070000410079956},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.375},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36959999799728394},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C99613125","wikidata":"https://www.wikidata.org/wiki/Q165194","display_name":"Application programming interface","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C137364921","wikidata":"https://www.wikidata.org/wiki/Q27929394","display_name":"Parallel programming model","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C150495011","wikidata":"https://www.wikidata.org/wiki/Q128392","display_name":"Concurrent computing","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3784828.3786264","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3786264","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:publications/57003548-ce26-43b5-852c-a11c06ac09b9","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/57003548-ce26-43b5-852c-a11c06ac09b9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/57003548-ce26-43b5-852c-a11c06ac09b9","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/57003548-ce26-43b5-852c-a11c06ac09b9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3784828.3786264","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3786264","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1505706396","https://openalex.org/W1839773802","https://openalex.org/W1988425770","https://openalex.org/W2002257715","https://openalex.org/W2138075164","https://openalex.org/W2149629847","https://openalex.org/W2169631286","https://openalex.org/W2404184364","https://openalex.org/W2949223833","https://openalex.org/W3011938749","https://openalex.org/W3128575430","https://openalex.org/W4205364008","https://openalex.org/W4309341372","https://openalex.org/W4318711138","https://openalex.org/W4321636543","https://openalex.org/W4399409308","https://openalex.org/W4400624841","https://openalex.org/W4409760068","https://openalex.org/W7125608094"],"related_works":[],"abstract_inverted_index":{"Dense":[0],"matrix-vector":[1,67,163],"multiplication":[2,68,164],"is":[3,40,198],"a":[4,112,157,167],"fundamental":[5],"operation":[6],"widely":[7],"used":[8],"in":[9,97],"various":[10,83],"application":[11],"areas,":[12],"including":[13],"deep":[14],"learning,":[15],"computer":[16],"graphics,":[17],"and":[18,107,134,165,178,186,202],"numerical":[19,55],"analysis.":[20],"With":[21],"the":[22,52,62,74,77,142,203],"increasing":[23],"prevalence":[24],"of":[25,54,64,76,114,144,160,171,205],"large,":[26],"heterogeneous":[27,146],"high-performance":[28],"computing":[29,106],"(HPC)":[30],"systems":[31],"equipped":[32],"with":[33,82,118,153],"multiple":[34],"Graphical":[35],"Processing":[36],"Units":[37],"(GPUs),":[38],"it":[39],"crucial":[41],"to":[42,50,87],"analyze":[43],"effective":[44],"strategies":[45],"for":[46,94,200],"utilizing":[47],"these":[48,172],"accelerators":[49],"enhance":[51],"efficiency":[53],"computation.":[56],"This":[57],"study":[58,122],"thus":[59],"centers":[60],"on":[61,69,175],"intricacies":[63],"accelerating":[65],"dense":[66,162],"multi-GPU":[70],"systems.":[71],"We":[72,155],"explore":[73],"combination":[75],"Message":[78],"Passing":[79],"Interface":[80],"(MPI)":[81],"programming":[84,115,139,173],"models\u2014collectively":[85],"referred":[86],"as":[88,148],"MPI":[89],"+":[90],"X\u2014highlighting":[91],"its":[92],"potential":[93],"advancing":[95],"capabilities":[96],"large":[98,145],"HPC":[99],"environments,":[100],"particularly":[101],"those":[102],"aimed":[103],"at":[104],"exascale":[105],"beyond.":[108],"Here,":[109],"\"X\"":[110],"encompasses":[111],"range":[113],"models":[116,140,174],"compatible":[117],"MPI.":[119,154,188],"Specifically,":[120],"this":[121],"investigates":[123],"Compute":[124],"Unified":[125],"Device":[126],"Architecture":[127],"(CUDA),":[128],"HIP,":[129],"SYCL,":[130],"Open":[131,135],"Accelerators":[132],"(OpenACC),":[133],"Multi-Processing":[136],"(OpenMP)":[137],"Offloading":[138],"within":[141],"context":[143],"systems,":[147],"all":[149],"can":[150],"be":[151],"integrated":[152],"conduct":[156],"thorough":[158],"examination":[159],"parallel":[161],"provide":[166],"detailed":[168],"performance":[169],"analysis":[170],"NVIDIA,":[176],"AMD,":[177],"Intel":[179],"GPUs,":[180],"addressing":[181],"scenarios":[182],"involving":[183],"both":[184],"GPU-aware":[185],"non-GPU-aware":[187],"Our":[189],"findings":[190],"are":[191],"substantiated":[192],"by":[193],"openly":[194],"available":[195],"code,":[196],"which":[197],"essential":[199],"validation":[201],"progression":[204],"scientific":[206],"research.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2026-01-23T00:00:00"}